© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 78054
    Prev
    Next
    INDEX
    Explanations

    technical and named entities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ScopeManager
    -0.57
    inity
    -0.56
    CUT
    -0.54
    hobo
    -0.51
    oyo
    -0.51
    jspx
    -0.49
    Nya
    -0.49
    Personendaten
    -0.49
     impré
    -0.48
     nargin
    -0.48
    POSITIVE LOGITS
    ks
    0.72
    ter
    0.60
    FailureListener
    0.57
    taire
    0.52
    tact
    0.52
     tac
    0.52
    kta
    0.50
    k
    0.50
     متعلقه
    0.50
     للمعارف
    0.49
    Activations Density 0.000%

    No Known Activations